A Multi-Layer Approach to Superpixel-based Higher-order Conditional Random Field for Semantic Image Segmentation
This work addresses efficiency and complexity issues in semantic image segmentation for computer vision applications, representing an incremental improvement over existing CRF methods.
The paper tackles the high computational cost and complexity of learning higher-order potentials in superpixel-based higher-order conditional random fields (SP-HO-CRFs) for semantic image segmentation by proposing a multi-layer CRF framework that reformulates these cues into pairwise potentials, achieving accuracy enhancement without retraining on datasets like MSRC-21 and PASCAL VOC 2012.
Superpixel-based Higher-order Conditional random fields (SP-HO-CRFs) are known for their effectiveness in enforcing both short and long spatial contiguity for pixelwise labelling in computer vision. However, their higher-order potentials are usually too complex to learn and often incur a high computational cost in performing inference. We propose an new approximation approach to SP-HO-CRFs that resolves these problems. Our approach is a multi-layer CRF framework that inherits the simplicity from pairwise CRFs by formulating both the higher-order and pairwise cues into the same pairwise potentials in the first layer. Essentially, this approach provides accuracy enhancement on the basis of pairwise CRFs without training by reusing their pre-trained parameters and/or weights. The proposed multi-layer approach performs especially well in delineating the boundary details (boarders) of object categories such as "trees" and "bushes". Multiple sets of experiments conducted on dataset MSRC-21 and PASCAL VOC 2012 validate the effectiveness and efficiency of the proposed methods.